A tool that captures both the content and emotional tone of speech, sending structured voice analysis to any AI assistant via webhook.

Stars

65

7-day growth

No data

Forks

7

Open issues

0

License

NOASSERTION

Last updated

2026-07-12

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It bridges the gap between text-only communication and vocal emotion, addressing a deeply human need—to be heard not just in words but in tone, hesitation, and fatigue.

Who it is for

  • Developers building emotion-aware AI assistants or companions
  • People who struggle to articulate emotions through text (e.g., during depression or exhaustion)
  • Users of personal AI agents who want richer voice interaction
  • Researchers and hobbyists exploring multimodal voice analysis

Use cases

  • Integrate with a personal AI assistant that responds with empathy based on detected mood
  • Log emotional state over time from daily voice notes for self-reflection
  • Trigger different automations (e.g., lighting, music) based on vocal emotion
  • Provide real-time emotional context in teletherapy or support chatbots

Strengths

  • Privacy-first by default: audio is deleted after analysis unless the user opts in to keep it
  • Simple webhook integration makes it compatible with any existing AI backend
  • Combines speech transcription (Whisper) with acoustic analysis (librosa) and an LLM for nuanced emotion classification
  • Open source (MIT) with a clear, human-readable README that explains the motivation and architecture

Considerations

  • Requires ffmpeg for audio transcoding and HTTPS for production use with microphones
  • Emotion detection accuracy depends on the chosen LLM and may not be consistent across languages or accents
  • Not a complete chatbot—it only analyzes and forwards results; responses must be built separately

README quick start

快速开始

Description

turn tone of voice into something your AI can read

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482